Title :
Utilization-aware load balancing for the energy efficient operation of the big.LITTLE processor
Author :
Myungsun Kim ; Kibeom Kim ; Geraci, James R. ; Seongsoo Hong
Author_Institution :
Sch. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea
Abstract :
ARM´s big.LITTLE architecture introduces the opportunity to optimize power consumption by selecting the core type most suitable for a level of processing demand. To take advantage of this new axis of optimization, we introduce processor utilization into the Linux kernel´s load balancing algorithm. Our method improves the Linux kernel´s ability to schedule tasks in an energy efficient manner without making it directly aware of the available core types. Experimental results show an energy consumption improvement over the standard Linux scheduler up to 11.35% with almost no reduction in performance.
Keywords :
Linux; microcontrollers; operating system kernels; power aware computing; resource allocation; ARM big.LITTLE architecture; Linux kernel load balancing algorithm; Linux scheduler; big.LITTLE processor; energy efficient operation; power consumption; utilization-aware load balancing; Benchmark testing; Kernel; Linux; Load management; Multicore processing; Switches;
Conference_Titel :
Design, Automation and Test in Europe Conference and Exhibition (DATE), 2014
Conference_Location :
Dresden
DOI :
10.7873/DATE.2014.236